Parallel algorithm for prediction of variables in Simultaneous Equation Models

Abstract

Simultaneous equation models (SEM) are multivariate techniques that reflect the presence of jointly endogenous variables. Traditionally, these models have been used in economy, expanding in last decades into other disciplines. One of usefulness of the SEM is the future estimation of the endogenous variables once the coefficient of the model has been obtained. This estimation is made using the actual information of endogenous and exogenous variables, as well as the matrices of the model. This work studies a parallel algorithm for the future prediction of the endogenous variables of an SEM model. Experimental tests comparing shared memory and message passing algorithms are made when varying the problem size, in order to check the behaviour of the algorithm and the ideal resources to use.